playwright-cli

Warn

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the playwright-cli command-line tool to automate browser tasks, navigate URLs, and interact with page elements.
  • [REMOTE_CODE_EXECUTION]: The skill provides commands that allow for the execution of arbitrary JavaScript within the browser context.
  • Evidence: The eval and run-code commands in SKILL.md (e.g., playwright-cli run-code "async page => ...") enable dynamic script execution on navigated pages.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted data from external websites that is then processed by the agent.
  • Ingestion points: Data enters the agent's context through playwright-cli snapshot, playwright-cli console, and playwright-cli network commands in SKILL.md.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands in the captured content are present.
  • Capability inventory: The skill possesses powerful capabilities including arbitrary script execution (run-code, eval), file system access (upload), and full network navigation (open).
  • Sanitization: There is no evidence of sanitization, filtering, or validation of the captured web content before it is processed by the agent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 2, 2026, 07:11 PM
Security Audit — agent-trust-hub — playwright-cli